NE

neo_7b_sft_v0.1

NeoGGUF by legraphistaUpdated 2024-05-31
Download on Hugging Face
Parameters7.79B
Context8K
Layers28
Architecturellama
Smallest quant1.7 GB
Quick answer

neo_7b_sft_v0.1 needs about 6.8 GB of memory at IQ3_M (a 3.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 1.7 GB (IQ1_S) to 15.6 GB.

7.79B parameter Neo model fine‑tuned for instruction following

neo_7b_sft_v0.1 is a 7.79B parameter model based on the Neo family. It is trained with a 8192 token context window and released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations for llama.cpp inference.

Good at

  • Instruction following
  • Chat‑style dialogue
  • General language tasks

Limits

  • No vision support
  • Requires 8k context for full performance
  • Apache‑2.0 license limits commercial use without attribution

Best for

  • Local chatbots on mid‑range GPUs
  • Research prototypes needing a 7B model
  • Educational demos of instruction‑tuned LLMs

Who it’s for. Developers and researchers who need a 7B instruction‑tuned model that can run on local hardware. The model is suitable for projects that require an open‑source license and moderate VRAM usage.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.7 GB 5.0 GB
Fits Get file →
IQ1_M1.9 GB 5.2 GB
Fits Get file →
IQ2_XXS2.1 GB 5.5 GB
Fits Get file →
IQ2_XS2.4 GB 5.7 GB
Fits Get file →
IQ2_S2.5 GB 5.8 GB
Fits Get file →
IQ2_M2.7 GB 6.0 GB
Fits Get file →
Q2_K_S2.7 GB 6.0 GB
Fits Get file →
Q2_K2.9 GB 6.2 GB
Fits Get file →
IQ3_XXS3.0 GB 6.4 GB
Fits Get file →
IQ3_XS3.3 GB 6.6 GB
Fits Get file →
IQ3_S3.4 GB 6.7 GB
Fits Get file →
Q3_K_S3.4 GB 6.7 GB
Fits Get file →
IQ3_M3.5 GB 6.8 GB
Fits Get file →
Q3_K3.8 GB 7.1 GB
Fits Get file →
Q3_K_L4.1 GB 7.4 GB
Tight Get file →
IQ4_XS4.2 GB 7.5 GB
Tight Get file →
IQ4_NL4.4 GB 7.8 GB
Tight Get file →
Q4_K_S4.5 GB 7.8 GB
Tight Get file →
Q4_K4.7 GB 8.1 GB
Too big Get file →
Q5_K_S5.4 GB 8.7 GB
Too big Get file →
Q5_K5.5 GB 8.9 GB
Too big Get file →
Q6_K6.4 GB 9.7 GB
Too big Get file →
Q8_08.3 GB 11.6 GB
Too big Get file →
BF1615.6 GB 18.9 GB
Too big Get file →
—15.6 GB 18.9 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XS (2.36 GB) or Q2_K_S (2.71 GB). If 12 GB is available, IQ3_XS (3.25 GB) or Q3_K_S (3.43 GB) provide better quality. For 16 GB or more, Q4_K (4.74 GB) or Q5_K (5.54 GB) offer higher fidelity. Memory estimates are approximate.

What GPU do you need for neo_7b_sft_v0.1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q2_K_S (2.7 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_S (4.5 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 11.6 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (15.6 GB file, about 18.9 GB in use).

Which neo_7b_sft_v0.1 quant should you choose?

IQ3_M (3.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 1.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.79B
Layers28
Trained context8,192 tokens
KV cache (fp16)336 KB per token

Source

Quantized bylegraphista
FamilyNeo
Licenseapache-2.0
Downloads (HF)1,200
Last updated2024-05-31

Frequently asked questions about neo_7b_sft_v0.1

How much VRAM does neo_7b_sft_v0.1 need?

About 6.8 GB at IQ3_M with an 8K context window. That is the 3.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run neo_7b_sft_v0.1 on an 8 GB GPU?

Yes, with Q4_K_S: the 4.5 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of neo_7b_sft_v0.1 GGUF?

It depends on the quant: IQ1_S is 1.7 GB, IQ1_M is 1.9 GB, IQ2_XXS is 2.1 GB, IQ2_XS is 2.4 GB, IQ2_S is 2.5 GB, IQ2_M is 2.7 GB and 19 more.

What context length does neo_7b_sft_v0.1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.8 GB at 8K and 2.8 GB at 8K.

Where can I download neo_7b_sft_v0.1 GGUF?

The files are on Hugging Face in the legraphista/neo_7b_sft_v0.1-IMat-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does neo_7b_sft_v0.1 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run neo_7b_sft_v0.1 on 8 GB VRAM?

Yes, use a quantization such as IQ2_XS or Q2_K_S which fit within 8 GB VRAM with an estimated 5.7 GB usage at 8k context.

Does the model support image input?

No, neo_7b_sft_v0.1 is a text‑only model and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use with attribution.

Other GGUFs of neo_7b_sft_v0.1

Similar models

Browse all →

More from legraphista

All by legraphista →

More Neo models

All Neo →

Other small models

All small models →